© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12147
    Prev
    Next
    INDEX
    Explanations

    terms related to access permissions and IAM policies in AWS

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Permissions, rights, access control

    np_acts-logits-general · gemini-2.0-flash

    access and permissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.70
     ModelExpression
    -0.67
    TagHelpers
    -0.65
    ">:
    -0.63
    ValueStyle
    -0.61
     nahilalakip
    -0.59
     discontinuous
    -0.59
     Référence
    -0.58
    NewUrlParser
    -0.58
     تانيه
    -0.55
    POSITIVE LOGITS
     access
    1.39
     Access
    1.23
     permissions
    1.22
    access
    1.19
     permission
    1.17
    Access
    1.12
     доступа
    1.04
     authorization
    1.03
     acceso
    1.02
     privileges
    1.01
    Activations Density 0.446%

    No Known Activations