© 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. 17-GEMMASCOPE-RES-16K
    6. 4803
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.70
    følgelig
    -0.70
    hhhhhhhh
    -0.68
    NOPQRST
    -0.61
    addPreferredGap
    -0.59
    cshtml
    -0.59
    attles
    -0.58
    IUrlHelper
    -0.58
    RetentionPolicy
    -0.58
    SharedDtor
    -0.58
    POSITIVE LOGITS
     himself
    2.52
     herself
    2.45
     themselves
    2.42
     own
    2.41
     yourself
    2.25
     ourselves
    2.23
     myself
    2.14
     itself
    2.08
    himself
    2.08
     Himself
    2.05
    Activations Density 0.514%

    No Known Activations