Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 7607
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical processes and methodologies in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rinol
    -0.45
    nef
    -0.42
    半
    -0.41
    ะ
    -0.41
     cho
    -0.41
     digress
    -0.39
    Cho
    -0.39
    とり
    -0.39
     particular
    -0.38
    kak
    -0.38
    POSITIVE LOGITS
    awaiter
    0.70
    OGND
    0.69
    tagHelperRunner
    0.68
     Pristupljeno
    0.68
    WEBPACK
    0.67
     PLWABN
    0.66
    ล้ว
    0.65
    NameInMap
    0.65
    UnsafeEnabled
    0.64
    protoimpl
    0.64
    Activations Density 1.034%

    No Known Activations