© 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. 14-GEMMASCOPE-RES-16K
    6. 7034
    Prev
    Next
    INDEX
    Explanations

    relevant nouns and determiners in a structured context

    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
    dhury
    -0.47
     r
    -0.44
    uebe
    -0.44
     the
    -0.43
    ASHI
    -0.43
    .
    -0.43
     master
    -0.43
     faisons
    -0.42
     there
    -0.42
     top
    -0.41
    POSITIVE LOGITS
    SharedDtor
    1.02
    ArgsConstructor
    0.84
    сылкі
    0.83
    awtextra
    0.83
     незавершена
    0.83
    RenderAtEndOf
    0.82
    SourceChecksum
    0.79
     Normdatei
    0.78
    Personendaten
    0.77
    WebControls
    0.77
    Activations Density 0.401%

    No Known Activations