© 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-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8722
    Prev
    Next
    INDEX
    Explanations

    structured code blocks and indentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    <eos>
    -0.38
    ↵↵
    -0.36
     for
    -0.34
    The
    -0.32
    and
    -0.31
    ※
    -0.31
    for
    -0.31
    <0xF0>
    -0.30
    ↵
    -0.30
    <h4>
    -0.30
    POSITIVE LOGITS
    ſelben
    1.14
    <unused79>
    1.09
    <unused51>
    1.09
    <unused74>
    1.09
    <unused23>
    1.09
    <unused14>
    1.09
    <unused8>
    1.08
    <unused16>
    1.08
    <unused3>
    1.08
    [@BOS@]
    1.08
    Activations Density 0.014%

    No Known Activations