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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12749
    Prev
    Next
    INDEX
    Explanations

    references to user permissions and access control in technology contexts

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

    Code, registry keys, and directory paths

    np_acts-logits-general · gemini-2.0-flash

    Active Directory and system queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -1.09
    exitRule
    -0.60
     onBackPressed
    -0.59
    jsxFileName
    -0.56
     Mula
    -0.55
     imgur
    -0.54
    ynos
    -0.53
    Blockly
    -0.53
    ьаж
    -0.53
     Patreon
    -0.52
    POSITIVE LOGITS
    évaluateur
    0.70
     Ker
    0.56
    memberOf
    0.55
    memberof
    0.55
     Active
    0.52
     LDAP
    0.52
    anias
    0.52
    inguished
    0.51
    LDAP
    0.50
    Ker
    0.50
    Activations Density 0.482%

    No Known Activations