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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 6335
    Prev
    Next
    INDEX
    Explanations

    action verbs related to processes or operations

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

    Code and string creation

    np_acts-logits-general · gemini-2.0-flash

    verbs describing actions and their results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tal
    -0.64
    B
    -0.63
    pr
    -0.59
    be
    -0.59
    sof
    -0.59
    the
    -0.59
    式
    -0.58
    R
    -0.57
    PR
    -0.56
    ec
    -0.56
    POSITIVE LOGITS
    ')")
    1.06
    altes
    0.95
     itſelf
    0.94
    ']")
    0.93
     }}-
    0.91
    citenamefont
    0.91
     كومونز
    0.90
    )]:
    0.90
    ]")
    0.88
    )')
    0.87
    Activations Density 0.586%

    No Known Activations