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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 7880
    Prev
    Next
    INDEX
    Explanations

    instances of the word "through" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.34
    1.3%
    1909
    +0.13
    0.5%
    1334
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1909
    +0.34
    0.05
    1092
    +0.13
    0.04
    1334
    +0.11
    0.03
    Negative Logits
    <bos>
    -1.26
    fetch
    -0.57
     Cal
    -0.57
    1
    -0.57
    4
    -0.57
    cal
    -0.56
    0
    -0.56
    et
    -0.55
    Cal
    -0.54
    2
    -0.54
    POSITIVE LOGITS
     napoli
    1.20
     outlander
    1.17
     soggior
    1.15
     venuto
    1.11
     peugeot
    1.08
     tramont
    1.08
     paradiso
    1.07
     cioc
    1.07
     conflic
    1.07
     dovr
    1.06
    Activations Density 0.136%

    No Known Activations