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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 833
    Prev
    Next
    INDEX
    Explanations

    technical terms related to devices and inventions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    2019
    +0.18
    0.7%
    50
    +0.12
    0.5%
    1535
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1699
    +0.18
    0.06
    2019
    +0.12
    0.06
    917
    +0.11
    0.04
    Negative Logits
    <bos>
    -2.67
     intersper
    -1.60
     quitted
    -1.37
     hentai
    -1.21
     encomp
    -1.16
     shenan
    -1.16
     thut
    -1.14
     seiz
    -1.11
     disbur
    -1.08
     forbear
    -1.08
    POSITIVE LOGITS
    letterSpacing
    0.70
    Voci
    0.65
     SqlDbType
    0.65
    fontStyle
    0.64
     useHistory
    0.62
     makeStyles
    0.61
    setAlpha
    0.61
     useNavigate
    0.60
    paddingVertical
    0.59
    TypedValue
    0.59
    Activations Density 0.341%

    No Known Activations